gigablast/open-source-search-engine
1
0
Fork 0
mirror of https://github.com/gigablast/open-source-search-engine.git synced 2024-10-05 04:37:39 +03:00
Code Issues Projects Releases Wiki Activity

be able to turn off getting of link info

Browse Source 
for faster rebuild of GI.
This commit is contained in:
Matt Wells 2014-12-13 13:17:26 -08:00
parent 8e6ae1f202
commit 584d48edc7
2 changed files with 21 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
Parms.cpp
View File

@ -17011,12 +17011,17 @@ void Parms::init ( ) {
m->m_title = "enable link voting";
m->m_desc = "If this is true Gigablast will "
"index hyper-link text and use hyper-link "
"structures to boost the quality of indexed documents.";
"structures to boost the quality of indexed documents. "
"You can disable this when doing a ton of injections to "
"keep things fast. Then do a posdb (index) rebuild "
"after re-enabling this when you are done injecting. Or "
"if you simply do not want link voting this will speed up"
"your injections and spidering a bit.";
m->m_cgi = "glt";
m->m_off = (char *)&cr.m_getLinkInfo - x;
m->m_type = TYPE_BOOL;
m->m_def = "1";
m->m_flags = PF_HIDDEN | PF_NOSAVE;
m->m_flags = PF_CLONE|PF_API;//PF_HIDDEN | PF_NOSAVE;
m->m_page = PAGE_SPIDER;
m->m_obj = OBJ_COLL;
m++;

18
XmlDoc.cpp
View File

@ -13658,12 +13658,25 @@ LinkInfo s_dummy2;
// . returns -1 if blocked, will re-call m_callback
LinkInfo *XmlDoc::getLinkInfo1 ( ) {
if ( m_linkInfo1Valid && ptr_linkInfo1 )
return ptr_linkInfo1;
// just return nothing if not doing link voting
CollectionRec *cr = getCollRec();
if ( ! cr ) return NULL;
// to keep things fast we avoid getting link info for some collections
if ( ! m_linkInfo1Valid && ! cr->m_getLinkInfo ) {
ptr_linkInfo1 = NULL;
m_linkInfo1Valid = true;
}
// sometimes it is NULL in title rec when setting from title rec
if ( m_linkInfo1Valid && ! ptr_linkInfo1 ) {
memset ( &s_dummy2 , 0 , sizeof(LinkInfo) );
s_dummy2.m_lisize = sizeof(LinkInfo);
ptr_linkInfo1 = &s_dummy2;
size_linkInfo1 = sizeof(LinkInfo);
return ptr_linkInfo1;
}
// return if we got it
@ -13673,9 +13686,6 @@ LinkInfo *XmlDoc::getLinkInfo1 ( ) {
// change status
setStatus ( "getting local inlinkers" );
CollectionRec *cr = getCollRec();
if ( ! cr ) return NULL;
XmlDoc **od = getOldXmlDoc ( );
if ( ! od || od == (XmlDoc **)-1 ) return (LinkInfo *)od;
int32_t *sni = getSiteNumInlinks();
@ -13805,7 +13815,7 @@ LinkInfo *XmlDoc::getLinkInfo1 ( ) {
// onlyNeedGoodInlinks = false;
//}
// call it
// call it. this is defined in Linkdb.cpp
char *url = getFirstUrl()->getUrl();
if ( ! getLinkInfo ( &m_tmpBuf12,
&m_mcast12,